feature(nyz): add policy gradient algo implementation

[PaParaZz1]

Description

add policy gradient (REINFORCE) algo

LunarLander result:

Related Issue

#517

TODO

Check List

• merge the latest version source branch/repo, and resolve all the conflicts
• pass style check
• pass all the tests

[codecov]

Codecov Report

Merging #544 (db3290a) into main (756b912) will increase coverage by 0.26%.
The diff coverage is 88.00%.

❗ Current head db3290a differs from pull request most recent head 4aecd40. Consider uploading reports for the commit 4aecd40 to get more accurate results

@@            Coverage Diff             @@
##             main     #544      +/-   ##
==========================================
+ Coverage   85.33%   85.60%   +0.26%     
==========================================
  Files         529      532       +3     
  Lines       43543    44442     +899     
==========================================
+ Hits        37157    38043     +886     
- Misses       6386     6399      +13     

Flag	Coverage Δ
unittests	85.60% <88.00%> (+0.26%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
ding/model/common/__init__.py	100.00% <ø> (ø)
ding/torch_utils/data_helper.py	76.69% <0.00%> (-0.66%)	⬇️
ding/policy/base_policy.py	74.01% <33.33%> (-0.43%)	⬇️
ding/model/common/head.py	98.43% <71.42%> (-0.77%)	⬇️
ding/entry/tests/test_serial_entry_onpolicy.py	81.81% <77.77%> (-0.54%)	⬇️
ding/policy/pg.py	88.88% <88.88%> (ø)
ding/model/template/tests/test_pg.py	90.90% <90.90%> (ø)
ding/model/template/pg.py	94.11% <94.11%> (ø)
ding/config/config.py	83.90% <100.00%> (+0.05%)	⬆️
ding/model/template/__init__.py	100.00% <100.00%> (ø)
... and 20 more

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.